
=== Start adding workers ===
=> Add worker SGDMWorker(index=0, momentum=0.9)
=> Add worker SGDMWorker(index=1, momentum=0.9)
=> Add worker SGDMWorker(index=2, momentum=0.9)
=> Add worker SGDMWorker(index=3, momentum=0.9)
=> Add worker SGDMWorker(index=4, momentum=0.9)
=> Add worker SGDMWorker(index=5, momentum=0.9)
=> Add worker SGDMWorker(index=6, momentum=0.9)
=> Add worker SGDMWorker(index=7, momentum=0.9)
=> Add worker SGDMWorker(index=8, momentum=0.9)
=> Add worker SGDMWorker(index=9, momentum=0.9)
=> Add worker BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f0f691ba9d0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3109 top1=  9.6875

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 1 has targets: tensor([2, 1, 4, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([3, 1, 4, 1, 3], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 0, 0, 1], device='cuda:0')
Worker 4 has targets: tensor([2, 1, 1, 4, 2], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')
Worker 6 has targets: tensor([9, 9, 6, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([7, 5, 7, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([8, 9, 9, 5, 7], device='cuda:0')
Worker 9 has targets: tensor([8, 8, 7, 5, 9], device='cuda:0')
Worker 10 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 11 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.3790 top1= 51.8750
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.8183 top1= 74.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3697 top1= 73.1671


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0391 top1= 48.2472


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9951 top1= 40.1342

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.5144 top1= 85.0000
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3698 top1= 88.7500
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.2772 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0326 top1= 81.0697


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8400 top1= 49.3790


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5923 top1= 44.4311

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.2595 top1= 93.4375
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.2868 top1= 91.2500
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2062 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9121 top1= 83.2031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1171 top1= 49.6995


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8684 top1= 44.9519

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.2416 top1= 92.5000
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.2254 top1= 92.1875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1571 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8562 top1= 83.8341


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3073 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1294 top1= 45.4026

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1867 top1= 94.3750
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.1811 top1= 93.1250
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1351 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8095 top1= 84.1747


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3730 top1= 49.9499


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1927 top1= 45.5128

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1476 top1= 95.3125
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.1560 top1= 94.0625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1080 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7640 top1= 85.2865


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4958 top1= 50.0501


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3101 top1= 45.6731

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.1341 top1= 96.5625
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.1332 top1= 95.0000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.1103 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7291 top1= 85.1562


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6538 top1= 50.1002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5094 top1= 45.7432

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.1260 top1= 96.8750
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.1110 top1= 96.2500
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0975 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7286 top1= 85.4067


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5841 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4380 top1= 45.9335

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.1212 top1= 96.5625
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.1123 top1= 95.6250
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0684 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7101 top1= 85.3866


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6102 top1= 50.1502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4063 top1= 46.1038

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.1048 top1= 96.5625
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0930 top1= 96.5625
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0647 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7064 top1= 85.7472


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6138 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4911 top1= 46.2340

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0896 top1= 97.5000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0842 top1= 96.5625
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0759 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6886 top1= 86.1979


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6344 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5841 top1= 46.3141

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0821 top1= 96.8750
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0719 top1= 97.8125
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0567 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6640 top1= 86.9892


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7003 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6106 top1= 46.4643

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0687 top1= 97.8125
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0722 top1= 96.8750
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0617 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6577 top1= 86.1979


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8574 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8309 top1= 46.4643

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0619 top1= 98.4375
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0605 top1= 97.8125
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0491 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6369 top1= 87.2897


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8802 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7854 top1= 46.4243

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0617 top1= 98.7500
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0618 top1= 97.8125
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0377 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6462 top1= 86.7588


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8994 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7138 top1= 46.5645

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0648 top1= 97.8125
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0572 top1= 98.7500
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0314 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6294 top1= 87.1995


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9212 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7362 top1= 46.5946

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0481 top1= 99.0625
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0508 top1= 98.1250
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0309 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6220 top1= 87.2997


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8383 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8465 top1= 46.7147

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0448 top1= 99.0625
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0429 top1= 98.7500
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0341 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6215 top1= 87.2396


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9348 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8902 top1= 46.7648

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0517 top1= 98.4375
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0407 top1= 98.7500
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0244 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5978 top1= 87.5701


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0521 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0236 top1= 46.9251

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0382 top1= 99.0625
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0386 top1= 99.6875
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0237 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5900 top1= 87.7604


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0843 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1164 top1= 46.8650

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0457 top1= 98.4375
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0377 top1= 98.7500
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0238 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5875 top1= 87.7304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1159 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1309 top1= 46.8249

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0402 top1= 98.1250
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0318 top1= 99.3750
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0203 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5807 top1= 87.5501


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1283 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0567 top1= 46.9651

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0377 top1= 99.3750
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0362 top1= 99.0625
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0192 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5859 top1= 87.4700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1220 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0948 top1= 47.0653

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0379 top1= 99.3750
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0246 top1= 99.6875
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0208 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5799 top1= 87.5801


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1064 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1473 top1= 47.0553

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0330 top1= 99.0625
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0304 top1= 99.0625
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0152 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5584 top1= 87.9808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2283 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3125 top1= 47.0653

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0197 top1= 99.6875
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0164 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0136 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5618 top1= 87.4700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2638 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3738 top1= 47.0753

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0283 top1= 99.3750
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0256 top1= 99.6875
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0134 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5478 top1= 88.4115


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2270 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2816 top1= 47.1855

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0230 top1= 99.3750
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0215 top1= 99.6875
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0146 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5409 top1= 88.1811


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2029 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2464 top1= 47.1254

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0236 top1= 99.0625
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0192 top1= 99.6875
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0145 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5539 top1= 87.9207


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3389 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2862 top1= 47.2055

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0247 top1= 99.3750
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0168 top1= 99.6875
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0114 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5341 top1= 88.9724


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2076 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2888 top1= 47.1554

